Because of the lackluster system performance across the board the past 12 months I am in the process of an extended review of the methodologies in system development. The primary focus will be making sure that out of sample performance from the design point holds up year after year and that everything is re-optimized at least once a year, but not to include data from the current year. The first system to undergo this review will be ES1 which was the first system ever developed. If this system cannot hold up under more rigorous backtesting and walked forward optimization, then the counter trend systems such as this may just have to be taken out of the mix altogether. Poor performance of the counter trend systems has been the biggest point of failure in the current environment.
More to follow....
No comments:
Post a Comment